tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": true
  },
  "clean_up_tokenization_spaces": false,
  "add_prefix_space": false,
  "legacy": false,
  "model_max_length": 1000000000000000019884624838656,
  "sp_model_kwargs": {},
  "tokenizer_class": "IndexTokenizer",
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_index.IndexTokenizer",
      null
      ]
  }
}